Skip to content

GH-51090: [CI][C++] Fix shellcheck errors in cpp/build-support/fuzzing/generate_corpuses.sh #51091

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kou merged 13 commits into from
Sep 8, 2026
+34 −37
Merged

GH-51090: [CI][C++] Fix shellcheck errors in cpp/build-support/fuzzing/generate_corpuses.sh #51091

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
af8db02
GH-51090: [CI][C++] Fix shellcheck errors in cpp/build-support/fuzzin…
hiroyuki-sato Aug 31, 2026
5de572f
GH-51090: [CI][C++] Fix shellcheck errors in cpp/build-support/fuzzin…
hiroyuki-sato Aug 31, 2026
f6caada
Use array
hiroyuki-sato Sep 1, 2026
b3f458c
Fix SC2198
hiroyuki-sato Sep 1, 2026
a9f358f
fix invalid quote
hiroyuki-sato Sep 1, 2026
47b45b5
Add comment
hiroyuki-sato Sep 1, 2026
c22d546
fix quote
hiroyuki-sato Sep 1, 2026
3a17d27
Use shell glob instead of find command
hiroyuki-sato Sep 6, 2026
7cec9c6
Revert "Use shell glob instead of find command"
hiroyuki-sato Sep 7, 2026
baf3185
Use while .. read
hiroyuki-sato Sep 7, 2026
ddb0907
Fix missing variable
hiroyuki-sato Sep 7, 2026
354d28a
Remove find result check
hiroyuki-sato Sep 7, 2026
700bf78
Remove while..read
hiroyuki-sato Sep 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 1 addition & 7 deletions .pre-commit-config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -288,13 +288,7 @@ repos:
(
?^c_glib/.*\.sh$|
?^ci/.*\.sh$|
?^cpp/build-support/build-lz4-lib\.sh$|
?^cpp/build-support/build-zstd-lib\.sh$|
?^cpp/build-support/get-upstream-commit\.sh$|
?^cpp/build-support/run-test\.sh$|
?^cpp/build-support/update-flatbuffers\.sh$|
?^cpp/build-support/update-thrift\.sh$|
?^cpp/build-support/vendor-flatbuffers\.sh$|
?^cpp/build-support/.*\.sh$|
?^cpp/examples/minimal_build/run\.sh$|
?^cpp/examples/tutorial_examples/run\.sh$|
?^cpp/src/arrow/flight/sql/odbc/install/mac/postinstall$|
Expand Down
63 changes: 33 additions & 30 deletions cpp/build-support/fuzzing/generate_corpuses.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ set -ex
CORPUS_DIR=/tmp/corpus
PANDAS_DIR=/tmp/pandas

ARROW_ROOT=$(cd $(dirname "$BASH_SOURCE")/../../..; pwd)
ARROW_ROOT=$(cd "$(dirname "${BASH_SOURCE[0]}")/../../.." && pwd)
ARROW_CPP=$ARROW_ROOT/cpp
OUT=$1

Expand All @@ -39,51 +39,54 @@ OUT=$1

# Arrow IPC

rm -rf ${CORPUS_DIR}
${OUT}/arrow-ipc-generate-fuzz-corpus -stream ${CORPUS_DIR}
rm -rf "${CORPUS_DIR}"
"${OUT}/arrow-ipc-generate-fuzz-corpus" -stream "${CORPUS_DIR}"
# Add "golden" IPC integration files
IPC_INTEGRATION_FILES=$(find ${ARROW_ROOT}/testing/data/arrow-ipc-stream/integration -name "*.stream")
[ -z "${IPC_INTEGRATION_FILES}" ] && exit 1
# Several IPC integration files can have the same name, make sure
# they all appear in the corpus by numbering the duplicates.
cp --backup=numbered ${IPC_INTEGRATION_FILES} ${CORPUS_DIR}
${ARROW_CPP}/build-support/fuzzing/pack_corpus.py ${CORPUS_DIR} ${OUT}/arrow-ipc-stream-fuzz_seed_corpus.zip
find "${ARROW_ROOT}/testing/data/arrow-ipc-stream/integration" \
-name "*.stream" \
-exec cp --backup=numbered '{}' "${CORPUS_DIR}" \;

rm -rf ${CORPUS_DIR}
${OUT}/arrow-ipc-generate-fuzz-corpus -file ${CORPUS_DIR}
IPC_INTEGRATION_FILES=$(find ${ARROW_ROOT}/testing/data/arrow-ipc-stream/integration -name "*.arrow_file")
[ -z "${IPC_INTEGRATION_FILES}" ] && exit 1
cp --backup=numbered ${IPC_INTEGRATION_FILES} ${CORPUS_DIR}
${ARROW_CPP}/build-support/fuzzing/pack_corpus.py ${CORPUS_DIR} ${OUT}/arrow-ipc-file-fuzz_seed_corpus.zip
"${ARROW_CPP}/build-support/fuzzing/pack_corpus.py" "${CORPUS_DIR}" "${OUT}/arrow-ipc-stream-fuzz_seed_corpus.zip"

rm -rf ${CORPUS_DIR}
${OUT}/arrow-ipc-generate-tensor-fuzz-corpus -stream ${CORPUS_DIR}
${ARROW_CPP}/build-support/fuzzing/pack_corpus.py ${CORPUS_DIR} ${OUT}/arrow-ipc-tensor-stream-fuzz_seed_corpus.zip
rm -rf "${CORPUS_DIR}"
"${OUT}/arrow-ipc-generate-fuzz-corpus" -file "${CORPUS_DIR}"

find "${ARROW_ROOT}/testing/data/arrow-ipc-stream/integration" \
-name "*.arrow_file" \
-exec cp --backup=numbered '{}' "${CORPUS_DIR}" \;

"${ARROW_CPP}/build-support/fuzzing/pack_corpus.py" "${CORPUS_DIR}" "${OUT}/arrow-ipc-file-fuzz_seed_corpus.zip"

rm -rf "${CORPUS_DIR}"
"${OUT}/arrow-ipc-generate-tensor-fuzz-corpus" -stream "${CORPUS_DIR}"
"${ARROW_CPP}/build-support/fuzzing/pack_corpus.py" "${CORPUS_DIR}" "${OUT}/arrow-ipc-tensor-stream-fuzz_seed_corpus.zip"

# Parquet file-level fuzzer

rm -rf ${CORPUS_DIR}
${OUT}/parquet-arrow-generate-fuzz-corpus ${CORPUS_DIR}
rm -rf "${CORPUS_DIR}"
"${OUT}/parquet-arrow-generate-fuzz-corpus" "${CORPUS_DIR}"
# Add Parquet testing examples
cp ${ARROW_CPP}/submodules/parquet-testing/data/*.parquet ${CORPUS_DIR}
cp ${ARROW_CPP}/submodules/parquet-testing/bad_data/*.parquet ${CORPUS_DIR}
${ARROW_CPP}/build-support/fuzzing/pack_corpus.py ${CORPUS_DIR} ${OUT}/parquet-arrow-fuzz_seed_corpus.zip
cp "${ARROW_CPP}"/submodules/parquet-testing/data/*.parquet "${CORPUS_DIR}"
cp "${ARROW_CPP}"/submodules/parquet-testing/bad_data/*.parquet "${CORPUS_DIR}"
"${ARROW_CPP}/build-support/fuzzing/pack_corpus.py" "${CORPUS_DIR}" "${OUT}/parquet-arrow-fuzz_seed_corpus.zip"

# Parquet encoding fuzzer

rm -rf ${CORPUS_DIR}
${OUT}/parquet-generate-encoding-fuzz-corpus ${CORPUS_DIR}
${ARROW_CPP}/build-support/fuzzing/pack_corpus.py ${CORPUS_DIR} ${OUT}/parquet-encoding-fuzz_seed_corpus.zip
"${OUT}/parquet-generate-encoding-fuzz-corpus" "${CORPUS_DIR}"
"${ARROW_CPP}/build-support/fuzzing/pack_corpus.py" "${CORPUS_DIR}" "${OUT}/parquet-encoding-fuzz_seed_corpus.zip"

# CSV

rm -rf ${PANDAS_DIR}
git clone --depth=1 https://github.com/pandas-dev/pandas ${PANDAS_DIR}
rm -rf "${PANDAS_DIR}"
git clone --depth=1 https://github.com/pandas-dev/pandas "${PANDAS_DIR}"

rm -rf ${CORPUS_DIR}
${OUT}/arrow-csv-generate-fuzz-corpus ${CORPUS_DIR}
rm -rf "${CORPUS_DIR}"
"${OUT}/arrow-csv-generate-fuzz-corpus" "${CORPUS_DIR}"
# Add examples from arrow-testing repo
cp ${ARROW_ROOT}/testing/data/csv/*.csv ${CORPUS_DIR}
cp "${ARROW_ROOT}"/testing/data/csv/*.csv "${CORPUS_DIR}"
# Add examples from Pandas test suite
find ${PANDAS_DIR}/ -name "*.csv" -exec cp --backup=numbered '{}' ${CORPUS_DIR} \;
${ARROW_CPP}/build-support/fuzzing/pack_corpus.py ${CORPUS_DIR} ${OUT}/arrow-csv-fuzz_seed_corpus.zip
find "${PANDAS_DIR}/" -name "*.csv" -exec cp --backup=numbered '{}' "${CORPUS_DIR}" \;
"${ARROW_CPP}/build-support/fuzzing/pack_corpus.py" "${CORPUS_DIR}" "${OUT}/arrow-csv-fuzz_seed_corpus.zip"
Loading